Thanks to open-access corpora including Universal Dependencies and OntoNotes, HanLP 2.1 now supports 10 joint tasks on 104 languages: tokenization, lemmatization, part-of-speech tagging, token feature extraction, dependency parsing, constituency parsing, semantic role labeling, semantic dependency parsing and abstract meaning representation (AMR) parsing.
In return, we offer free RESTful APIs to the open-source community licensed under CC BY-NC-SA 4.0.
How to Apply
Our RESTful server employs HTTP Basic Authentication which protects our server from being abused. To apply for an
auth, please fill up the following form and send it to @hanlpbot via private message (new users need to stay on the forum for several minutes in order to be able to send PMs). We will send back your auth via PMs in one business day once approved.
## Name ## Organization ## Phone ## Research Field ## Apply the following APIs <!-- Put an x into each bracket you want to check --> - [ ] Tokenization - [ ] Part-of-Speech tagging - [ ] Lemmatization - [ ] Universal Dependencies Features Extraction - [ ] Named Entity Recognition - [ ] Dependency Parsing - [ ] Constituency Parsing - [ ] Semantic Role Labeling - [ ] Semantic Dependency Parsing - [ ] Abstract Meaning Representation Parsing ## Disclaimer The APIs are provided "as is", without warranty of any kind, express or implied, including but not limited to the warranties of merchantability, fitness for a particular purpose and noninfringement. In no event shall the authors or service providers be liable for any claim, damages or other liability, whether in an action of contract, tort or otherwise, arising from, out of or in connection with the APIs or the use or other dealings in the APIs. I fully understand and accept the above disclaimer and apply for an auth token licenced under CC BY-NC-SA 4.0. ## Signature
We carry out a rate limit per minute to your client for dispersing traffic over time. Your quota is a summation of the following items based on your contribution to the open-source community.
|Use HanLP, which is a contribution by itself||2|
|Trust Level 1 on our forum||2|
|Trust Level 2 on our forum||8|
|Trust Level 3 on our forum||16|
|Every 10 likes on our forum||+2|
|Educational Institution (add a .edu email)||+4|
|Star HanLP on GitHub||+4|
|Fork HanLP on GitHub||+4|
|Every bug found for HanLP on GitHub||+4|
|Every PR made to HanLP on GitHub||+4|
For each request, at most 32 sentences or ~15000 characters can be parsed so this quota is reasonable for research purposes.
Please keep contributing to the open-source world and we’ll update your quota on a daily basis.
See https://hanlp.hankcs.com/docs/ for how to use the RESTful APIs.